diff --git a/built-in-nodes/AnimaLLLiteApply.mdx b/built-in-nodes/AnimaLLLiteApply.mdx index 184e25c35..8c035918f 100644 --- a/built-in-nodes/AnimaLLLiteApply.mdx +++ b/built-in-nodes/AnimaLLLiteApply.mdx @@ -31,4 +31,4 @@ AnimaLLLiteApply applies a lightweight animation patch to a diffusion model, ena > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/AnimaLLLiteApply/en.md) --- -**Source fingerprint (SHA-256):** `291dc6a6619faab1c1100110c71c47381addcd80dbaf933dd8025a376bc2bee7` +**Source fingerprint (SHA-256):** `48e455b767509a5a8c329365d5ffded86d6f4545d575c9fdc5ffbaf4da7c2287` diff --git a/built-in-nodes/ApplyTextureToMesh.mdx b/built-in-nodes/ApplyTextureToMesh.mdx index 44132f0bc..7e996b433 100644 --- a/built-in-nodes/ApplyTextureToMesh.mdx +++ b/built-in-nodes/ApplyTextureToMesh.mdx @@ -30,4 +30,4 @@ Note: When any of `metallic`, `roughness`, or `occlusion` is connected, all thre > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ApplyTextureToMesh/en.md) --- -**Source fingerprint (SHA-256):** `f91985ef686beddccc41a72614b3d263b4e0d9f1a156db6017d620de26d7b6cf` +**Source fingerprint (SHA-256):** `7492922c9c7c0117366cb8b9017fc192eb8dd6b6594fd429044d60408693210e` diff --git a/built-in-nodes/BakeTextureFromVoxel.mdx b/built-in-nodes/BakeTextureFromVoxel.mdx index 140ed6e64..e9e79fc07 100644 --- a/built-in-nodes/BakeTextureFromVoxel.mdx +++ b/built-in-nodes/BakeTextureFromVoxel.mdx @@ -1,12 +1,12 @@ --- title: "BakeTextureFromVoxel - ComfyUI Built-in Node Documentation" -description: "This node bakes PBR textures onto a 3D mesh using the mesh's existing UV layout." +description: "This node bakes PBR textures onto a 3D mesh using the mesh’s existing UV layout." sidebarTitle: "BakeTextureFromVoxel" icon: "circle" mode: wide --- -This node bakes PBR textures onto a 3D mesh using the mesh's existing UV layout. It samples color and material attributes from a sparse voxel volume at each texel and outputs a base color image plus metallic and roughness maps. It does not unwrap the mesh, so a UV unwrap node must be connected upstream. +This node bakes PBR textures onto a 3D mesh using the mesh’s existing UV layout. It samples color and material attributes from a sparse voxel volume at each texel and outputs a base color image plus metallic and roughness maps. It does not unwrap the mesh, so a UV unwrap node must be connected upstream. ## Inputs @@ -34,4 +34,4 @@ Notes: > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/BakeTextureFromVoxel/en.md) --- -**Source fingerprint (SHA-256):** `419f9e064edaeb9db8d5e052cf57a3b8b77bf7e025e8a0fc9aa0e1919c06b51c` +**Source fingerprint (SHA-256):** `080dcb670620f1cb97523d04fc45293e03d139e513845d0fa7b1c4d2f8bdf32d` diff --git a/built-in-nodes/ComfyCloudFlux2TextToImageNode.mdx b/built-in-nodes/ComfyCloudFlux2TextToImageNode.mdx new file mode 100644 index 000000000..825c3f64d --- /dev/null +++ b/built-in-nodes/ComfyCloudFlux2TextToImageNode.mdx @@ -0,0 +1,30 @@ +--- +title: "ComfyCloudFlux2TextToImageNode - ComfyUI Built-in Node Documentation" +description: "Runs the Flux 2 dev text-to-image model on a Comfy Cloud GPU and returns the generated image." +sidebarTitle: "ComfyCloudFlux2TextToImageNode" +icon: "circle" +mode: wide +--- + +Runs the Flux 2 dev text-to-image model on a Comfy Cloud GPU and returns the generated image. The `turbo` option applies the Turbo LoRA with a short schedule for a much quicker run at the cost of a little fidelity; turning it off performs the full-length dev pass without the LoRA. This is a beta node set, billed by how long it runs in credits. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | The text prompt describing the image to generate. Leading and trailing whitespace is removed before submission. | STRING | Yes | 1 to 4096 characters | +| `seed` | Random seed that controls the generated result for reproducibility (default: 42). | INT | Yes | 0 to 18446744073709551615 | +| `aspect_ratio` | Aspect ratio of the output image (default: "1:1"). | COMBO | Yes | "1:1"
"3:4"
"2:3"
"3:2"
"4:3"
"16:9"
"9:16"
"21:9" | +| `megapixels` | Total pixel budget. 1.0 is about 1024x1024 at a square ratio (default: 1.0). | FLOAT | Yes | 0.1 to 16.0 (step 0.1) | +| `turbo` | Run the Turbo LoRA on a short schedule, trading a little fidelity for a much quicker run. Off runs the full dev pass with no LoRA (default: True). | BOOLEAN | Yes | True / False | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `IMAGE` | The image generated from the text prompt, returned as a ComfyUI image tensor that can be passed to other nodes. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyCloudFlux2TextToImageNode/en.md) + +--- +**Source fingerprint (SHA-256):** `1b51a8ab89ae7c355dec4256a1a25a09a15e192c72fc8d1862c652dbdf337fcb` diff --git a/built-in-nodes/ComfyCloudMageFlowTextToImageNode.mdx b/built-in-nodes/ComfyCloudMageFlowTextToImageNode.mdx new file mode 100644 index 000000000..33c41c877 --- /dev/null +++ b/built-in-nodes/ComfyCloudMageFlowTextToImageNode.mdx @@ -0,0 +1,27 @@ +--- +title: "ComfyCloudMageFlowTextToImageNode - ComfyUI Built-in Node Documentation" +description: "This node generates an image from a text prompt by sending the request to the Mage-Flow text-to-image workflow in the Comfy Cloud." +sidebarTitle: "ComfyCloudMageFlowTextToImageNode" +icon: "circle" +mode: wide +--- + +This node generates an image from a text prompt by sending the request to the Mage-Flow text-to-image workflow in the Comfy Cloud. It runs the full 30-step generation pass rather than the faster distilled turbo pass, and it accepts a negative prompt so you can describe content you do not want in the final image. The negative prompt is supported in this 30-step mode; per the node summary, the distilled turbo variant cannot make good use of it. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | The text description of the image to generate. | STRING | Yes | Free-form text | +| `negative_prompt` | Text describing content that should not appear in the generated image. This input is used during the standard 30-step generation pass, but the distilled turbo variant does not use negative prompts well. | STRING | No | Free-form text | + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `image` | The image generated from the provided text prompt and negative prompt. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyCloudMageFlowTextToImageNode/en.md) + +--- +**Source fingerprint (SHA-256):** `80f4ecf1df3f2c46d94138f8ada817e12cc49e69e69a001630776ed644868367` diff --git a/built-in-nodes/ComfyCloudMageFlowTurboTextToImageNode.mdx b/built-in-nodes/ComfyCloudMageFlowTurboTextToImageNode.mdx new file mode 100644 index 000000000..7a40cf64e --- /dev/null +++ b/built-in-nodes/ComfyCloudMageFlowTurboTextToImageNode.mdx @@ -0,0 +1,30 @@ +--- +title: "ComfyCloudMageFlowTurboTextToImageNode - ComfyUI Built-in Node Documentation" +description: "This Comfy Cloud node generates an image from a text prompt using the Mage-Flow Turbo workflow (mage-flow-turbo/text-to-image)." +sidebarTitle: "ComfyCloudMageFlowTurboTextToImageNode" +icon: "circle" +mode: wide +--- + +This Comfy Cloud node generates an image from a text prompt using the Mage-Flow Turbo workflow (`mage-flow-turbo/text-to-image`). It runs a distilled version of the Mage-Flow model that generates the image in 4 steps at a cfg value of 1, taking roughly one seventh of the GPU time of a full Mage-Flow pass, which makes it the variant intended for fast iteration. + +## Inputs + +The node class itself does not declare input widgets in the available source; its input schema is inherited from the shared base class `_ComfyCloudMageFlowNode`, whose definition is not included in the source snapshot. Based on the node summary and the text-to-image workflow name, the node takes a text prompt describing the image to generate. + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | The text prompt describing the image to generate. The exact parameter name is set by the inherited `_ComfyCloudMageFlowNode` base schema and may differ from this label. | STRING | Yes | Free text | + +Note: Additional input parameters may exist in the inherited base node definition, which is not available in the provided source. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `IMAGE` | The image generated from the text prompt. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyCloudMageFlowTurboTextToImageNode/en.md) + +--- +**Source fingerprint (SHA-256):** `8d867a0c906028597ef52c75f5c9a994fdc00211c7aae410ffca8204943f0c34` diff --git a/built-in-nodes/ComfyCloudZImageTurboNode.mdx b/built-in-nodes/ComfyCloudZImageTurboNode.mdx new file mode 100644 index 000000000..c2d2cf864 --- /dev/null +++ b/built-in-nodes/ComfyCloudZImageTurboNode.mdx @@ -0,0 +1,31 @@ +--- +title: "ComfyCloudZImageTurboNode - ComfyUI Built-in Node Documentation" +description: "This node generates an image from a text prompt using the Z-Image Turbo model, which completes in just 8 steps." +sidebarTitle: "ComfyCloudZImageTurboNode" +icon: "circle" +mode: wide +--- + +This node generates an image from a text prompt using the Z-Image Turbo model, which completes in just 8 steps. The generation runs remotely on Comfy Cloud GPUs and is billed by GPU time, making this one of the quickest and cheapest options here for iterating on image ideas. Once the generation finishes, the node downloads the finished image for use in your workflow. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Text prompt describing the image to generate. Accepts multi-line input and is trimmed before submission. Must not be empty after trimming. | STRING | Yes | 1 - 4096 characters | +| `seed` | Random seed used to control generation reproducibility. Changing it produces a different variation. Includes a control-after-generate option. Default: 42. | INT | No | 0 - 18446744073709551615 | +| `aspect_ratio` | Aspect ratio of the generated image. Default: "1:1". | COMBO | No | "1:1"
"3:4"
"2:3"
"3:2"
"4:3"
"16:9"
"9:16"
"21:9" | +| `megapixels` | Total pixel budget. 1.0 is about 1024x1024 at a square ratio. Default: 1.0. | FLOAT | No | 0.1 - 16.0
(step of 0.1) | + +Note: Input values are validated before the generation is submitted. The `prompt` must contain between 1 and 4,096 characters after whitespace is trimmed, `aspect_ratio` must be one of the listed options, and `megapixels` must be entered in increments of 0.1. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `IMAGE` | The generated image returned as an image tensor, ready for further image processing or saving nodes. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyCloudZImageTurboNode/en.md) + +--- +**Source fingerprint (SHA-256):** `9c78bf9aca5800212d1c5a8f9581dc6c154a82220cd60a8b55ebe74111d2f542` diff --git a/built-in-nodes/ComfyMathExpression.mdx b/built-in-nodes/ComfyMathExpression.mdx index 4c3a07aab..44fe48f15 100644 --- a/built-in-nodes/ComfyMathExpression.mdx +++ b/built-in-nodes/ComfyMathExpression.mdx @@ -1,35 +1,37 @@ --- title: "ComfyMathExpression - ComfyUI Built-in Node Documentation" -description: "The ComfyMathExpression node evaluates a mathematical formula using a set of input values." +description: "The ComfyMathExpression node evaluates a mathematical formula that you write as text." sidebarTitle: "ComfyMathExpression" icon: "circle" mode: wide --- -The ComfyMathExpression node evaluates a mathematical formula using a set of input values. You can write an expression using variable names (like `a`, `b`, `c`), and the node will calculate the result. It supports dynamically adding as many input values as needed for your calculation. +The ComfyMathExpression node evaluates a mathematical formula that you write as text. The formula can reference the node's input values using letter names such as `a`, `b`, `c`, and you can add as many input values as needed through the growable `values` group. The calculation result is returned simultaneously as a floating-point number, an integer, and a boolean value. ## Inputs | Parameter | Description | Data Type | Required | Range | |-----------|-------------|-----------|----------|-------| -| `expression` | The mathematical formula to evaluate. You can use variable names that correspond to the input values (default: "a + b"). | STRING | Yes | N/A | -| `values` | A set of numeric or boolean inputs that can be dynamically added. Each input is assigned a letter from the alphabet (a, b, c, ...) to be used as a variable in the expression. At least one input value is required. | FLOAT, INT, BOOLEAN | No | N/A | +| `expression` | The mathematical formula to evaluate, written as text (for example `a + b`), using the letter names of the input values as variables. Multiline input. (default: "a + b") | STRING | Yes | N/A | +| `values` | Growable group of input values that provides the variables for the expression. Each value added to the group automatically gets the next lowercase letter name starting at `a` (`a`, `b`, `c`, ...), and that name can then be used inside `expression`. Each item accepts a number (INT or FLOAT) or a boolean (TRUE/FALSE). | FLOAT, INT, BOOLEAN | Yes | 1 to 26 values, named `a` to `z` | -**Parameter Constraints:** -* The `expression` parameter cannot be empty or contain only whitespace. -* The expression must evaluate to a finite numeric result (INT or FLOAT). Boolean or other non-numeric results will cause an error. -* The input values for the `values` parameter can be numbers (INT or FLOAT) or boolean values (TRUE/FALSE). -* At least one input value must be provided in the `values` group. +### Notes and constraints + +- `expression` cannot be empty or contain only whitespace. +- The expression must evaluate to a numeric result (INT or FLOAT). If the result is a different type, such as text, the node raises an error. +- The numeric result must be finite and convertible to a float. Results that are too large or non-finite cause an error. +- The whole set of input values is also available inside the expression under the variable name `values` (as a list), so expressions such as `sum(values)` are possible. +- The following math functions are available inside the expression: `sum`, `min`, `max`, `abs`, `round`, `pow`, `sqrt`, `ceil`, `floor`, `log`, `log2`, `log10`, `sin`, `cos`, `tan`, `int`, `float`. ## Outputs | Output Name | Description | Data Type | |-------------|-------------|-----------| -| `FLOAT` | The result of the mathematical expression as a floating-point number. | FLOAT | -| `INT` | The result of the mathematical expression as an integer. | INT | -| `BOOL` | The result of the mathematical expression as a boolean value. | BOOLEAN | +| `FLOAT` | The result of the expression as a floating-point number. | FLOAT | +| `INT` | The result of the expression converted to an integer, with the decimal part truncated. | INT | +| `BOOL` | The result converted to a boolean value: TRUE when the numeric result is not zero, FALSE when it is zero. | BOOLEAN | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfyMathExpression/en.md) --- -**Source fingerprint (SHA-256):** `d3b47ddb7bc40318d35ad09fb53793cea25e9a9b310ab47aaf937781e3ad2b73` +**Source fingerprint (SHA-256):** `4c77e9834fe7341143352f95ed8808dc81def3361b197c67e33a531bb3696d71` diff --git a/built-in-nodes/ComfySwitchNode.mdx b/built-in-nodes/ComfySwitchNode.mdx index 9aa50f3b9..b16ae49a2 100644 --- a/built-in-nodes/ComfySwitchNode.mdx +++ b/built-in-nodes/ComfySwitchNode.mdx @@ -6,7 +6,7 @@ icon: "circle" mode: wide --- -The Switch node selects between two possible inputs based on a boolean condition. It outputs the `on_true` input when the `switch` is enabled, and the `on_false` input when the `switch` is disabled. Only the selected branch is evaluated, so the other input is not required. This allows you to create conditional logic and choose different data paths in your workflow. +The Switch node selects between two possible inputs based on a boolean condition. When `switch` is enabled (true), it passes the `on_true` input through to the output; when disabled (false), it passes `on_false`. Only the selected branch is evaluated, so the other input does not need to be connected. ## Inputs @@ -16,15 +16,15 @@ The Switch node selects between two possible inputs based on a boolean condition | `on_false` | The data to be passed to the output when the `switch` is disabled (false). This input is only required when the `switch` is false. | MATCH_TYPE | No | | | `on_true` | The data to be passed to the output when the `switch` is enabled (true). This input is only required when the `switch` is true. | MATCH_TYPE | No | | -**Note on Input Requirements:** The `on_false` and `on_true` inputs are conditionally required. The node will request the `on_true` input only when the `switch` is true, and the `on_false` input only when the `switch` is false. Both inputs must be of the same data type and must match the output data type. +**Note on Input Requirements:** The `on_false` and `on_true` inputs are conditionally required. The node requests the `on_true` input only when the `switch` is true, and the `on_false` input only when the `switch` is false. Both inputs must be of the same data type and must match the output data type. If the selected input is not connected, the node outputs no value. ## Outputs | Output Name | Description | Data Type | | --- | --- | --- | -| `output` | The selected data. This will be the value from the `on_true` input if the `switch` is true, or the value from the `on_false` input if the `switch` is false. | MATCH_TYPE | +| `output` | The selected data. This is the value from the `on_true` input when the `switch` is true, or the value from the `on_false` input when the `switch` is false. | MATCH_TYPE | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ComfySwitchNode/en.md) --- -**Source fingerprint (SHA-256):** `d0adda02e7f997f27182cb26e11e934660ae5bd80f3091bed2fed7c981632ce5` +**Source fingerprint (SHA-256):** `42c442efeda0197d950702c52647233dee1a30216fb07e1ce4bc844784a6c5f2` diff --git a/built-in-nodes/GetImageSize.mdx b/built-in-nodes/GetImageSize.mdx index 9ead44fea..629d9da14 100644 --- a/built-in-nodes/GetImageSize.mdx +++ b/built-in-nodes/GetImageSize.mdx @@ -1,28 +1,28 @@ --- title: "GetImageSize - ComfyUI Built-in Node Documentation" -description: "The GetImageSize node extracts the dimensions and batch information from an input image." +description: "GetImageSize reads an input image and returns its width, height, and batch size." sidebarTitle: "GetImageSize" icon: "circle" mode: wide --- -The GetImageSize node extracts the dimensions and batch information from an input image. It returns the width, height, and batch size of the image while also displaying this information as progress text on the node interface. The original image data passes through unchanged. +GetImageSize reads an input image and returns its width, height, and batch size. The node also displays these measured values directly on the node interface. ## Inputs | Parameter | Description | Data Type | Required | Range | -| --- | --- | --- | --- | --- | -| `image` | The input image from which to extract size information | IMAGE | Yes | - | +|-----------|-------------|-----------|----------|-------| +| `image` | The input image from which the width, height, and batch size are extracted | IMAGE | Yes | - | ## Outputs | Output Name | Description | Data Type | -| --- | --- | --- | +|-------------|-------------|-----------| | `width` | The width of the input image in pixels | INT | | `height` | The height of the input image in pixels | INT | -| `batch_size` | The number of images in the batch | INT | +| `batch_size` | The number of images contained in the input batch | INT | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/GetImageSize/en.md) --- -**Source fingerprint (SHA-256):** `251c8480ccb1a1462a8d7656ce2b7ef33f2b9f6527b8b306a0850af16ef4094d` +**Source fingerprint (SHA-256):** `dc29add37a3362384e63cb1e57f03758a82f77811c78797fdffd486462cb19b8` diff --git a/built-in-nodes/HiDreamO1ReferenceImages.mdx b/built-in-nodes/HiDreamO1ReferenceImages.mdx index 734a4660e..e87682e9b 100644 --- a/built-in-nodes/HiDreamO1ReferenceImages.mdx +++ b/built-in-nodes/HiDreamO1ReferenceImages.mdx @@ -1,14 +1,12 @@ --- title: "HiDreamO1ReferenceImages - ComfyUI Built-in Node Documentation" -description: "Documentation for HiDreamO1ReferenceImages node." +description: "This node attaches reference images to both positive and negative conditioning, so downstream nodes can use them to guide generation." sidebarTitle: "HiDreamO1ReferenceImages" icon: "circle" mode: wide --- -## Overview - -Attach reference images to both positive and negative conditioning. This node lets you provide 1 to 10 reference images; a single image is used for instruction-based editing, while multiple images (2-10) enable subject-driven personalization. +This node attaches reference images to both positive and negative conditioning, so downstream nodes can use them to guide generation. Reference images are applied in the numeric order of their input sockets. If no reference images are connected, the positive and negative conditioning pass through unchanged. ## Inputs @@ -16,9 +14,9 @@ Attach reference images to both positive and negative conditioning. This node le | --- | --- | --- | --- | --- | | `positive` | The positive conditioning to attach reference images to. | CONDITIONING | Yes | - | | `negative` | The negative conditioning to attach reference images to. | CONDITIONING | Yes | - | -| `images` | Reference images. 1 image = instruction edit; 2-10 images = multi reference. | IMAGE | Yes | 1 to 10 images | +| `images` | Reference images are used in numeric socket order. When images are supplied, they are attached to both the positive and negative conditioning. | IMAGE | No | 0 to 100 images (`image_1` to `image_100`) | -**Note on `images` parameter:** This is an autogrow input that accepts between 1 and 10 images. The images are labeled `image_1` through `image_10`. You must provide at least 1 image. The number of images determines the mode of operation: a single image is used for edit instructions, while multiple images (2-10) are used for subject-driven personalization. +**Note on `images` parameter:** This is an autogrow input that provides numbered sockets `image_1` through `image_100`. Images are used in numeric socket order. The input is optional: if no reference images are connected, the node returns the `positive` and `negative` conditioning unchanged. When images are connected, the same set of reference images is attached to both outputs, and the negative conditioning is also marked as negative before the images are attached. ## Outputs @@ -30,4 +28,4 @@ Attach reference images to both positive and negative conditioning. This node le > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/HiDreamO1ReferenceImages/en.md) --- -**Source fingerprint (SHA-256):** `f05f6be19df8b8697a98507163e8f60fd0cf2048c81f92597d2ae0a3395b8c6d` +**Source fingerprint (SHA-256):** `07f9f0ea19957523e95d04b9086dc994807bb0cd5262fe798dc784c1ecb4920d` diff --git a/built-in-nodes/ImageCompositor.mdx b/built-in-nodes/ImageCompositor.mdx index 46dcf556d..776b95fec 100644 --- a/built-in-nodes/ImageCompositor.mdx +++ b/built-in-nodes/ImageCompositor.mdx @@ -6,7 +6,7 @@ icon: "circle" mode: wide --- -This node combines multiple image layers into a single composited image. It takes a layer stack built with the Add Layer node and optionally a saved composition from the compositor editor, then blends the layers together using their placement, size, rotation, opacity, and blend mode settings. +This node combines multiple image layers into a single composited image. It takes a layer stack built with the Add Layer node and optionally applies saved composition settings from the compositor editor, blending the layers according to their placement, size, rotation, opacity, and blend mode. ## Inputs @@ -36,4 +36,4 @@ This node combines multiple image layers into a single composited image. It take > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/ImageCompositor/en.md) --- -**Source fingerprint (SHA-256):** `1eca5c151b3737ccf76e6fd7a83cd1458b2acc314609753d597eec711bcf4bd8` +**Source fingerprint (SHA-256):** `76e5e57ade89f9ee172c5e1f0b82579d846d15bafb52b2052246f1f2ad7f0034` diff --git a/built-in-nodes/LTXVContextWindows.mdx b/built-in-nodes/LTXVContextWindows.mdx index 409cad82a..e3123f080 100644 --- a/built-in-nodes/LTXVContextWindows.mdx +++ b/built-in-nodes/LTXVContextWindows.mdx @@ -34,4 +34,4 @@ This node sets context windows for LTXV-like models during sampling. It divides > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVContextWindows/en.md) --- -**Source fingerprint (SHA-256):** `ad0b8c54acaab1853f6fe98dbad675478f033caf867df954b40b7db5208f5ae4` +**Source fingerprint (SHA-256):** `148649d0a938e08c932a163f5d7614332626fba37b8f79db7f92bbcf422e692f` diff --git a/built-in-nodes/LTXVDurationPredictor.mdx b/built-in-nodes/LTXVDurationPredictor.mdx index 590e02dd6..c39849009 100644 --- a/built-in-nodes/LTXVDurationPredictor.mdx +++ b/built-in-nodes/LTXVDurationPredictor.mdx @@ -1,12 +1,12 @@ --- title: "LTXVDurationPredictor - ComfyUI Built-in Node Documentation" -description: "This node predicts the natural shot duration for a prompt using an LTX 2.4 duration head." +description: "This node predicts the natural shot duration for a text prompt using an LTX 2.4 duration head loaded with ModelPatchLoader, then snaps the result to the VAE's 8k+1 frame grid." sidebarTitle: "LTXVDurationPredictor" icon: "circle" mode: wide --- -This node predicts the natural shot duration for a prompt using an LTX 2.4 duration head. It converts the predicted duration into a frame count that fits the VAE's frame grid, using the supplied frame rate and minimum/maximum duration limits. +This node predicts the natural shot duration for a text prompt using an LTX 2.4 duration head loaded with ModelPatchLoader, then snaps the result to the VAE's 8k+1 frame grid. The prediction is converted into a frame count using the selected frame rate and the minimum and maximum duration limits. ## Inputs @@ -19,7 +19,7 @@ This node predicts the natural shot duration for a prompt using an LTX 2.4 durat | `min_seconds` | Minimum duration in seconds used when converting the prediction to a frame count (default: 1.0). | FLOAT | Yes | 0.5 to 120.0 | | `max_seconds` | Maximum duration in seconds used when converting the prediction to a frame count (default: 20.0). | FLOAT | Yes | 0.5 to 120.0 | -Note: The `duration_head` input must be an LTX 2.4 duration head loaded with ModelPatchLoader. If the connected model patch is not an LTX duration head, the node raises a ValueError. +Note: The `duration_head` input must be a model patch containing an LTX duration head. If the connected model patch is not an LTX duration head, the node raises a ValueError. Only the first conditioning entry is used — if `positive` contains a batch of more than one prompt, the node evaluates just the first one. ## Outputs @@ -31,4 +31,4 @@ Note: The `duration_head` input must be an LTX 2.4 duration head loaded with Mod > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LTXVDurationPredictor/en.md) --- -**Source fingerprint (SHA-256):** `ebbf6a2601a955122ab9862142aa475524c1f38403f4ef8dc9ffee6456ee8ce5` +**Source fingerprint (SHA-256):** `a4abb43128b8fe396e4c986d75028aea6bfdd9bb6fda07e24c88f8e04a61669e` diff --git a/built-in-nodes/LoadVideo.mdx b/built-in-nodes/LoadVideo.mdx index 378e3c2c8..429109f29 100644 --- a/built-in-nodes/LoadVideo.mdx +++ b/built-in-nodes/LoadVideo.mdx @@ -12,9 +12,9 @@ The Load Video node loads video files from the input directory and makes them av | Parameter | Description | Data Type | Required | Range | | --- | --- | --- | --- | --- | -| `file` | The video file to load from the input directory. The dropdown list is dynamically populated with all video files found in the ComfyUI input folder. | STRING | Yes | Multiple options available | +| `file` | The video file to load from the input directory. The dropdown list is dynamically populated with all video files found in the ComfyUI input folder, and new video files can be uploaded directly through the file picker. | COMBO | Yes | Multiple options available (all video files in the input directory) | -**Note:** The available options for the `file` parameter are dynamically populated from the video files present in the input directory. Only video files with supported content types are displayed. You can also upload a new video file directly through the node's file picker interface. +**Note:** The available options for the `file` parameter are dynamically populated from the video files present in the input directory. Only video files with supported content types are displayed. You can also upload a new video file directly through the node's file picker interface. If a previously selected video file can no longer be found, the node reports an invalid file error. ## Outputs @@ -25,4 +25,4 @@ The Load Video node loads video files from the input directory and makes them av > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/LoadVideo/en.md) --- -**Source fingerprint (SHA-256):** `7cdd0ed301e4545e38fb706231a18510088b76af4e843ccdfb3ae3cf8a912f49` +**Source fingerprint (SHA-256):** `dcdd252792ade2a106c11826bbe7344011f0bc08506b80d634043a4dc156e076` diff --git a/built-in-nodes/MaskPreview.mdx b/built-in-nodes/MaskPreview.mdx index 5f5cb5a16..19762e0a4 100644 --- a/built-in-nodes/MaskPreview.mdx +++ b/built-in-nodes/MaskPreview.mdx @@ -6,26 +6,26 @@ icon: "circle" mode: wide --- -The MaskPreview node displays a visual preview of the mask data directly in the ComfyUI interface, without saving it to the output directory. This lets you inspect the exact mask values at any point in your workflow. +The MaskPreview node displays a visual preview of the mask data directly in the ComfyUI interface, without saving it to the output directory. This lets you inspect the mask at any point in your workflow, while the mask also passes through the node unchanged so it can continue to be used downstream. ## Inputs | Parameter | Description | Data Type | Required | Range | |-----------|-------------|-----------|----------|-------| | `mask` | The mask data to preview | MASK | Yes | - | -| `filename_prefix` | Prefix for the preview filename (default: "ComfyUI") | STRING | No | - | +| `filename_prefix` | Filename prefix used for the preview (default: "ComfyUI") | STRING | No | - | | `prompt` | Prompt information for metadata (automatically provided) | PROMPT | No | - | | `extra_pnginfo` | Additional PNG information for metadata (automatically provided) | EXTRA_PNGINFO | No | - | -The `prompt` and `extra_pnginfo` inputs are hidden and are supplied automatically by the ComfyUI system; you do not need to connect them manually. +Only `mask` is a visible input that needs to be connected. The `filename_prefix`, `prompt`, and `extra_pnginfo` parameters are supplied by the system: `filename_prefix` falls back to its default value, while `prompt` and `extra_pnginfo` are hidden and provided automatically by the ComfyUI runtime. ## Outputs | Output Name | Description | Data Type | |-------------|-------------|-----------| -| `mask` | The mask data that was previewed, returned unchanged for further use in the workflow | MASK | +| `mask` | The same mask data that was previewed, returned unchanged so it can be used elsewhere in the workflow | MASK | > This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MaskPreview/en.md) --- -**Source fingerprint (SHA-256):** `3d4ecb8cd90c3ecbe9d3cff8f782062c582c7190d9f0e0ed069cba114d4beac5` +**Source fingerprint (SHA-256):** `fb7abe8cb6b5ac8a6a38e88ef90a146d16caf41d24c5de95309a94bc3c371d75` diff --git a/built-in-nodes/MetaMuseImageEditApi.mdx b/built-in-nodes/MetaMuseImageEditApi.mdx new file mode 100644 index 000000000..6f0ac0b8f --- /dev/null +++ b/built-in-nodes/MetaMuseImageEditApi.mdx @@ -0,0 +1,50 @@ +--- +title: "MetaMuseImageEditApi - ComfyUI Built-in Node Documentation" +description: "Edits or combines up to 10 reference images using a text prompt and Meta's Muse Image model." +sidebarTitle: "MetaMuseImageEditApi" +icon: "circle" +mode: wide +--- + +Edits or combines up to 10 reference images using a text prompt and Meta's Muse Image model. Describe the desired edit in the prompt and, when needed, refer to the reference images as `@Image1`, `@Image2`, and so on. The node uploads the reference images, calls the Meta Muse Image API, and returns the edited result as an image. + +## Inputs + +The node is controlled by a `model` selector. The model-specific inputs described below appear when a model is selected, and the reference images you connect can be grown or shortened as needed. + +### Common Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model` | Model to use. | DYNAMIC_COMBO | Yes | "muse-image-1.0" | + +### muse-image-1.0 Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Editing instructions. Supports `@Image1`-style references to the input images. Default: empty string. The prompt must contain at least one character. | STRING | Yes | Any text with a minimum length of 1 character | +| `aspect_ratio` | Aspect ratio of the output. Images are rendered at about 2.5 megapixels (1:1 is 1600x1600, 16:9 is 2048x1152); "auto" keeps the aspect ratio of the input. | COMBO | Yes | "auto"
"1:1"
"3:2"
"2:3"
"4:3"
"3:4"
"5:4"
"4:5"
"16:9"
"9:16"
"21:9"
"9:21"
"2:1"
"1:2" | +| `reasoning_strength` | How much the model thinks, plans and self-refines before rendering. | COMBO | Yes | "high"
"low" | +| `enable_web_search` | Lets the model search the web for facts and live information while planning the image. Default: true. | BOOLEAN | Yes | true or false (default: true) | +| `enable_image_search` | Lets the model search for reference images while planning the image. Default: true. | BOOLEAN | Yes | true or false (default: true) | +| `enable_shell` | Lets the model run code while planning, for precise layouts, charts and diagrams; when off, quantities and alignment are approximated. Default: true. | BOOLEAN | Yes | true or false (default: true) | +| `seed` | Seed to determine if node should re-run; the API has no seed, so actual results are nondeterministic regardless of this value. Default: 42. | INT | Yes | 0 to 2147483647 (step 1) | + +### Reference Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `images` | Growable slot: connect 1 to 10 reference images (`image_1` through `image_10`) to edit or combine. Refer to them in the prompt as `@Image1`, `@Image2`, ..., numbered in input order; a batched input counts once per image. | IMAGE | Yes | 1 to 10 reference images | + +Note: the prompt may not be empty, and each `@ImageN` reference it contains must match one of the connected images in input order (for example, `@Image1` is the first connected reference image). If the prompt references an image number that is not connected, or if more than 10 reference images are connected, the node raises an error. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `image` | The edited or combined image returned by the Muse Image model. If the API returns multiple images, they are returned as a batch. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MetaMuseImageEditApi/en.md) + +--- +**Source fingerprint (SHA-256):** `5c009ca45199f9c70465f12d48a46b685abebd0194c3d437121b9df0636dbea7` diff --git a/built-in-nodes/MetaMuseImageTextToImageApi.mdx b/built-in-nodes/MetaMuseImageTextToImageApi.mdx new file mode 100644 index 000000000..037ace896 --- /dev/null +++ b/built-in-nodes/MetaMuseImageTextToImageApi.mdx @@ -0,0 +1,44 @@ +--- +title: "MetaMuseImageTextToImageApi - ComfyUI Built-in Node Documentation" +description: "Meta Muse Image Text to Image generates images from a text prompt using Meta's Muse Image model." +sidebarTitle: "MetaMuseImageTextToImageApi" +icon: "circle" +mode: wide +--- + +Meta Muse Image Text to Image generates images from a text prompt using Meta's Muse Image model. The model reasons about the prompt before rendering, and can use web search, image search, and code execution while planning the image. The node calls the Muse Image API and returns the resulting image or images. + +## Inputs + +### Common Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model` | Model to use. | DYNAMIC_COMBO | Yes | `"muse-image-1.0"` | + +Selecting a model in the list shows the settings that model supports. The only available model is `muse-image-1.0`; its settings are listed below. + +### muse-image-1.0 Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `prompt` | Prompt describing the image. The model reasons about the prompt, and may use its built-in web and image search, before rendering. | STRING | Yes | Multiline text, minimum 1 character | +| `aspect_ratio` | Aspect ratio of the output. Images are rendered at about 2.5 megapixels (1:1 is 1600x1600, 16:9 is 2048x1152); "auto" lets the model choose from the prompt. | COMBO | Yes | `"auto"`
`"1:1"`
`"3:2"`
`"2:3"`
`"4:3"`
`"3:4"`
`"5:4"`
`"4:5"`
`"16:9"`
`"9:16"`
`"21:9"`
`"9:21"`
`"2:1"`
`"1:2"` | +| `reasoning_strength` | How much the model thinks, plans and self-refines before rendering. | COMBO | Yes | `"high"`
`"low"` | +| `enable_web_search` | Lets the model search the web for facts and live information while planning the image. | BOOLEAN | No | True
False (default: True) | +| `enable_image_search` | Lets the model search for reference images while planning the image. | BOOLEAN | No | True
False (default: True) | +| `enable_shell` | Lets the model run code while planning, for precise layouts, charts and diagrams; when off, quantities and alignment are approximated. | BOOLEAN | No | True
False (default: True) | +| `seed` | Seed to determine if node should re-run; the API has no seed, so actual results are nondeterministic regardless of this value. | INT | Yes | 0 – 2147483647 (default: 42) | + +Note: The prompt must contain at least one character. When `aspect_ratio` is set to "auto", no explicit size is sent to the API and the model decides the output size from the prompt. The `seed` parameter only controls when the node re-runs; it is not sent to the API, so the generated results are nondeterministic. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `image` | The generated image returned by the API, decoded and provided as a batched image. If the API response contains multiple images, they are combined into one batch. | IMAGE | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MetaMuseImageTextToImageApi/en.md) + +--- +**Source fingerprint (SHA-256):** `59ebd72fab3db44a35ceac723606de4eabb5fe2b690d0b701db50e0e22a9e699` diff --git a/built-in-nodes/MiniMaxH3FunControlNetApply.mdx b/built-in-nodes/MiniMaxH3FunControlNetApply.mdx new file mode 100644 index 000000000..003240945 --- /dev/null +++ b/built-in-nodes/MiniMaxH3FunControlNetApply.mdx @@ -0,0 +1,36 @@ +--- +title: "MiniMaxH3FunControlNetApply - ComfyUI Built-in Node Documentation" +description: "This node applies a MiniMax H3 Fun ControlNet to a text-to-video model as a model patch." +sidebarTitle: "MiniMaxH3FunControlNetApply" +icon: "circle" +mode: wide +--- + +This node applies a MiniMax H3 Fun ControlNet to a text-to-video model as a model patch. It can use an optional control video and an optional mask to steer generation, and it returns a patched copy of the model for further sampling. When the strength is set to 0, or when neither a control video nor a mask is provided, the input model is returned unchanged. + +## Inputs + +| Parameter | Description | Data Type | Required | Range | +|-----------|-------------|-----------|----------|-------| +| `model` | The diffusion model to which the MiniMax H3 Fun ControlNet patch is applied. | MODEL | Yes | N/A | +| `model_patch` | The MiniMax H3 Fun ControlNet patch whose control signals are injected into the model; it must be compatible with the given `model`. | MODEL_PATCH | Yes | N/A | +| `vae` | VAE used to encode the control and source video frames into the latent space expected by the model. | VAE | Yes | N/A | +| `strength` | Overall strength of the ControlNet effect. When set to 0, the node does nothing and returns the input model unchanged. (default: 1.0) | FLOAT | Yes | min 0.0, max 10.0, step 0.01 | +| `start_percent` | Start of the sampling range, expressed as a percentage of the sampling schedule, during which the ControlNet is active. It is converted internally to the equivalent sigma value. (default: 0.0) | FLOAT | Yes | min 0.0, max 1.0, step 0.001 | +| `end_percent` | End of the sampling range, expressed as a percentage of the sampling schedule, during which the ControlNet is active. It is converted internally to the equivalent sigma value. (default: 1.0) | FLOAT | Yes | min 0.0, max 1.0, step 0.001 | +| `control_video` | Optional video frames used as the ControlNet visual hint. The frames are resized to match the generated video and encoded with the `vae`. | IMAGE | No | N/A | +| `mask` | 1 marks the regions to regenerate. Mask values above 0.5 are treated as marked regions. | MASK | No | N/A | +| `source_video` | Video behind the mask; only read when a mask is given. | IMAGE | No | N/A | + +Note: For the patch to have an effect, `strength` must be greater than 0 and at least one of `control_video` or `mask` must be supplied. `source_video` is ignored unless `mask` is provided; if `mask` is given without `source_video`, the content behind the masked regions is treated as black. + +## Outputs + +| Output Name | Description | Data Type | +|-------------|-------------|-----------| +| `model` | A patched clone of the input model with the MiniMax H3 Fun ControlNet applied. If `strength` is 0, or no control video or mask is supplied, the original model is returned unchanged. | MODEL | + +> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/MiniMaxH3FunControlNetApply/en.md) + +--- +**Source fingerprint (SHA-256):** `e907fb8e5ae60663d1d10b315985695ee5d49397fef6bd76b0e723637457a74a` diff --git a/built-in-nodes/MiniMaxH3ReferenceToVideo.mdx b/built-in-nodes/MiniMaxH3ReferenceToVideo.mdx index c4ef8617c..33d6ca06e 100644 --- a/built-in-nodes/MiniMaxH3ReferenceToVideo.mdx +++ b/built-in-nodes/MiniMaxH3ReferenceToVideo.mdx @@ -6,39 +6,40 @@ icon: "circle" mode: wide --- -MiniMax H3 Reference to Video creates the text conditioning and the empty audio-video latent needed for MiniMax H3 reference-to-video generation. You provide a prompt plus optional reference images, videos, and audio clips, and the node encodes these references into tokens the model can use while generating. The prompt refers to the references with ``, `